Whisper Base EN (OnnxRuntime/DirectML) for Unity
They Love Games
$66.00
(no ratings)
Jump AssetStore
The Whisper Base English model runs on the ONNX Runtime accelerated by DirectML; ready-to-drop into a project for 64-bit Windows, providing fast speech-to-text with minimal setup, no extra downloads.This is an audio tool that is not affected by SRP compatiblity.This package currently supports 64-bit Windows for the Unity Editor and Standalone.SummaryWhisper Base EN (DirectML) is a turnkey Windows x64 Unity package that ships a single native DLL containing the OpenAI Whisper base.en model accelerated by ONNX Runtime + DirectML. It works offline in the Editor and Windows Standalone builds, enabling local speech-to-text from either audio clips or microphone input (continuous or push-to-talk). Drop it into your project to add language detection and transcription with minimal setup, plus ready-made example scenes and UI.User scenarios- You’re building a game and already support controller/keyboard/mouse, but you want speech input for accessibility and hands-free actions.- You want to create a voice-driven application that reacts to spoken commands without cloud latency.- You need to transcribe a batch of audio clips dynamically on a machine with no internet access, so you need a light-weight, fast, fully offline solution.- Single native DLL with Whisper base.en on ONNX Runtime + DirectML (offline, Windows x64).- Speech-to-text from audio clips (StreamingAssets) and live microphone input.- Microphone modes: continuous capture and push-to-talk.- Language detection and transcription from mono 16 kHz PCM.- Two example scenes: one for audio-clip translation; one for real-time and push-to-talk mic input.- Used AI to draft Python scripts that convert the MIT-licensed Whisper model to ONNX.- Guided “vibe coding” of the native DLL with ONNX Runtime, embedding the model, and wiring C# ↔ C++ calls.- Assisted Unity scripting to hook UI buttons, read microphone/audio clips, and build example scenes.- Helped outline unit tests; all code was manually reviewed and tested.- AI aided marketing images; final assets were hand-edited for quality.
